CN106096513A - Fingerprint identification method, fingerprint recognition system and electronic equipment - Google Patents
Fingerprint identification method, fingerprint recognition system and electronic equipment Download PDFInfo
- Publication number
- CN106096513A CN106096513A CN201610379150.7A CN201610379150A CN106096513A CN 106096513 A CN106096513 A CN 106096513A CN 201610379150 A CN201610379150 A CN 201610379150A CN 106096513 A CN106096513 A CN 106096513A
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- score
- fingerprint image
- image
- calculate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 230000013011 mating Effects 0.000 claims abstract description 4
- 238000012545 processing Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 abstract description 10
- 238000005516 engineering process Methods 0.000 description 7
- 230000008859 change Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000003825 pressing Methods 0.000 description 6
- 208000031481 Pathologic Constriction Diseases 0.000 description 4
- 210000001215 vagina Anatomy 0.000 description 4
- 230000008901 benefit Effects 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 230000026676 system process Effects 0.000 description 2
- 230000001166 anti-perspirative effect Effects 0.000 description 1
- 239000003213 antiperspirant Substances 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000000205 computational method Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/12—Fingerprints or palmprints
- G06V40/1365—Matching; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
Abstract
The invention discloses a kind of fingerprint identification method, comprise the following steps: step S1, obtain a fingerprint image.Step S2, calculate the quality comprehensive score of fingerprint image.Step S3, judge that the quality comprehensive score of fingerprint image is whether more than presetting score threshold.If step S4 judges that current finger print image information, whether more than presetting score threshold, is carried out mating and calculating matching score by the quality comprehensive score of fingerprint image with the information in fingerprint prestored.Step S5, judge that matching score is whether more than preset matching score threshold;If being carried out step S6, otherwise prompting fingerprint does not mates.Step S6, pass through fingerprint matching.In fingerprint identification process, it is ensured that use fingerprint image data and the preset fingerprint Data Matching of quality comprehensive score high value, reduce refusing sincere and improve the reliable of fingerprint recognition of fingerprint recognition checking.
Description
Technical field
The present invention relates to fingerprint image process field, particularly relate to a kind of fingerprint identification method, fingerprint knowledge
Other system and electronic equipment.
Background technology
Fingerprint identification technology has started to be widely used in mobile terminal, and the fingerprint for mobile terminal is known
Not, recognizer is then core technology.Due to the restriction of fingerprint collecting sensor, when finger is with antiperspirant
When stain, mud stain, discrimination can be substantially reduced, particularly this small size of mobile terminal fingerprint
Collecting device, recognizer relies on the fingerprint image quality of input especially, and the highest then discrimination of quality is more
Height, accuracy of system identification is the lowest, and the judgement to fingerprint image quality is particularly important the most before recognition.
At present, assessment fingerprint image quality is mainly by the method for statistics with study, such as HOG
(grey level histogram), SVM (support vector machine), PCA (principal component analysis), ANN (people
Artificial neural networks) etc..Above method or excessively simple, such as HOG, causes Quality estimation to be forbidden
Really.Or the process of calculating is the most complicated, such as ANN, needs longer calculating time and bigger depositing
Storage space, causes occupying too much mobile terminal calculating and processes resource.Fingerprint recognition is caused to be refused very
Rate is too high, or makes the fingerprint recognition proving time long, causes Consumer's Experience sense the best.
Summary of the invention
In consideration of it, the present invention provide one not by user's finger dry and wet degree, pressing area, dynamics,
The factor impacts such as environment, and fingerprint identification method efficiently and accurately, reliably.
The invention provides a kind of fingerprint identification method, comprise the following steps:
Step S1, obtain a fingerprint image;
Step S2, calculate the quality comprehensive score of fingerprint image;
Step S3, judge that the quality comprehensive score of fingerprint image is whether more than presetting score threshold;
If step S4 judges whether the quality comprehensive score of fingerprint image is more than presets score threshold,
Carry out mating and calculating matching score with the information in fingerprint prestored by current finger print image information;
Step S5, judge that matching score is whether more than preset matching score threshold;If the step of being carried out
S6, otherwise prompting fingerprint does not mates;
Step S6, pass through fingerprint matching.
In some embodiments, described fingerprint identification method is further comprising the steps of:
Step S7: the quality comprehensive score of fingerprint image is less than or equal to preset score threshold if judging,
Calculate the statistics number of fingerprint image quality score;
Step S8: judge that whether the quality score statistics number of fingerprint image is less than presetting statistics number
Threshold value, if being carried out step S1, otherwise prompting fingerprint does not mates.
In some embodiments, step S2: calculate the quality comprehensive score of fingerprint image, bag
Include:
Calculate the concordance score of the field of direction of fingerprint image;
Calculate the effective area score of fingerprint image;With
By the concordance score of the field of direction of calculated fingerprint image and calculated fingerprint image
The effective area score of picture is weighted summation to obtain the comprehensive score of fingerprint image quality.
In some embodiments, the concordance score of the field of direction of fingerprint image is calculated, including following
Step:
Step S21: calculate fingerprint image field of direction O (i, j);
Step S22: use fixed size window to field of direction O (i, j) carrying out slide calculate, it is thus achieved that
Concordance fingerprint image C (i, j);
Step S23: according to concordance fingerprint image C (i, j) the concordance score of calculated direction field.
In some embodiments, calculate the effective area score of fingerprint image, comprise the following steps:
Step S24: calculate horizontal direction gradient and the vertical gradient of fingerprint image;
Step S25: calculate fingerprint image gradient amplitude image A (i, j);
Step S26: (i j) carries out statistics of sliding to gradient amplitude image A with the window of fixed size;
Step S27: calculate the effective area score of fingerprint image according to slip statistical result.
Present invention also offers a kind of fingerprint recognition system, described fingerprint recognition system includes a fingerprint image
As processing module and a fingerprint sensing array, described fingerprint image processing module includes:
Fingerprint sensing array, for obtaining a frame fingerprint image;
Orientation field computation unit, calculates the concordance score of the field of direction of fingerprint image;
Effective area computing unit, calculates the effective area score of fingerprint image;
Score calculation unit, calculates the matter of fingerprint image according to concordance score and effective area score
Measure comprehensive score;
Judging unit, it is judged that whether quality comprehensive score is more than presetting score threshold, if being by fingerprint
Data are mated, and otherwise, prompting user fingerprints does not mates.
Further, described fingerprint image processing module includes: matching score computing module, it is judged that refer to
Stricture of vagina matching score whether preset matching score threshold, if then passing through fingerprint authentication.
Further, described orientation field computation unit passes through:
Calculate fingerprint image field of direction O (i, j);
To field of direction O, (i, j) carrying out slides calculates the window of employing fixed size, it is thus achieved that concordance refers to
Print image C (i, j);
According to concordance fingerprint image C (i, j) the concordance score of calculated direction field.
Further, described effective area computing unit passes through:
Calculate horizontal direction gradient and the vertical gradient of fingerprint image;
Calculate fingerprint image gradient amplitude image A (i, j);
With the window of fixed size, to gradient amplitude image A, (i j) carries out statistics of sliding;
The effective area score of fingerprint image is calculated according to slip statistical result.
The matter of fingerprint image is evaluated by fingerprint image effective area and two dimensions of orientation consistency
Amount.After calculating the effective area score and orientation consistency score obtaining fingerprint image, by two
Person is weighted summation can obtain the quality comprehensive score of final fingerprint image.In fingerprint recognition mistake
Cheng Zhong, it is ensured that use fingerprint image data and the preset fingerprint data of quality comprehensive score high value
Join, reduce refusing sincere and improve the reliable of fingerprint authentication in fingerprint identification process.
The present invention also provides for a kind of electronic equipment, and described electronic equipment includes described in above-mentioned any one
Fingerprint recognition system.
Although disclosing multiple embodiment, change including it, but by illustrate and describing the present invention
The following detailed description of disclosed explanation embodiment, other embodiments disclosed by the invention will be to affiliated neck
The technical staff in territory is apparent.Can be various obvious sides it will be recognized that the present invention is open
Face is revised, and all modifications is all without departing from the spirit and scope of the present invention.Correspondingly, accompanying drawing is with detailed
Describe and substantially should be considered illustrative and not restrictive.
Accompanying drawing explanation
Describing its example embodiment in detail by referring to accompanying drawing, the further feature of the present invention and advantage will
Become readily apparent from.
Fig. 1 is fingerprint identification method flow chart of the present invention.
Fig. 2 is that the concordance calculating fingerprint image orientation field in fingerprint identification process shown in Fig. 1 must shunt
Cheng Tu.
Fig. 3 is calculating fingerprint image effective area score flow chart in fingerprint identification process shown in Fig. 1.
Fig. 4 is the schematic diagram that definition preferably frame fingerprint image is converted to fingerprint image orientation field.
Fig. 5 is the schematic diagram that the frame fingerprint image that definition is not enough is converted to fingerprint image orientation field.
Fig. 6 is the schematic diagram of the fingerprint image effective area of a second-rate frame fingerprint image.
Fig. 7 is the module map of fingerprint recognition system of the present invention.
Detailed description of the invention
It is described more fully with example embodiment referring now to accompanying drawing.But, example embodiment energy
Enough implement in a variety of forms, and be not understood as limited to embodiment set forth herein;On the contrary, carry
Make the present invention will fully and completely for these embodiments, and by comprehensive for the design of example embodiment
Convey to those skilled in the art.The most identical reference represents same or similar knot
Structure.
Described feature or structure can be combined in one or more enforcement in any suitable manner
In mode.In the following description, it is provided that many details thus provide the embodiment party to the present invention
Fully understanding of formula.But, one of ordinary skill in the art would recognize that do not have in described specific detail
One or more, or use other structure, assembly etc., it is also possible to put into practice the technical side of the present invention
Case.In other cases, known features or operation are not shown in detail or describe to avoid obscuring this
Bright.
Owing to the quality of fingerprint image quality depends on that multiple angle is investigated, and not only certain dimension is permissible
Judge fingerprint image quality.Therefore the present invention comprehensive fingerprint image all angles determine fingerprint image picture element
The judge of amount.The evaluation method of the fingerprint image quality of the present invention is commented with reference to multiple factor multi-angles
Sentence to guarantee fingerprint image quality reliability and accuracy, provide fingerprint accurately for fingerprint recognition checking
Information.
Refer to Fig. 1, for fingerprint identification method flow chart of the present invention.Described fingerprint identification method includes
Following some steps, the content of each step described in detail below.
Step S1, obtain a fingerprint image.
Fingerprint image is to choose a frame fingerprint image from the positive negative sample of multiframe fingerprint image to comment
Valency.The positive negative sample of fingerprint image refers to the measured and ropy fingerprint image of matter.Fingerprint image is by people
Work selection, can be the on-the-spot artificial fingerprint image gathering acquisition, it is also possible to be showing from outside acquisition
The fingerprint image become.At the most preferably embodiment, by the electronic equipment root being provided with fingerprint sensor
Press according to user's finger, automatically obtain fingerprint image.
Step S2, calculate the comprehensive score of described fingerprint image quality.
In this step, weigh the aggregative indicator of a frame fingerprint image quality and mainly have two aspects: one
Aspect is in a frame fingerprint image, and non-fingerprint texture image pixel is in the ratio of whole fingerprint image pixel
The fewest more good, i.e. the effective area of fingerprint image.On the other hand the ridge and the Gu Yue that are fingerprint texture are clearly demarcated
The best, i.e. the definition of fingerprint image is the highest.
When user is carrying out fingerprint pressing operation, if the skin overdrying of user's finger or overly moist, by pressing through
Light or press the overweight definition that all can reduce fingerprint image.When user is when carrying out pressing operation, hands
Refer to pressing fingerprint sensor keep to the side edge then can cause gather fingerprint image effective area too small.
Therefore, calculating the comprehensive score of described fingerprint image quality, needing to calculate respectively fingerprint image
The concordance score of the field of direction and the effective area score of fingerprint image, then carried out both scores
Weighted sum can obtain comprehensive score S of final fingerprint image quality.
Wherein, the concordance of the field of direction calculating fingerprint image obtains as follows:
Step S21: calculate fingerprint image field of direction O (i, j).
Step S22: use fixed size window to field of direction O (i, j) carrying out slide calculate, it is thus achieved that
Concordance fingerprint image C (i, j).
At present, assess fingerprint image definition aspect, the method presently mainly utilizing self study, be somebody's turn to do
Method is the most complicated, is unfavorable for reducing system cost.Therefore can estimate that image is clear based on following methods
Clear degree, reaches the feature that the little accuracy of amount of calculation is high.
By use the window of fixed size to field of direction O of fingerprint image (i, j) carrying out slides calculates,
Acquisition concordance image C (i, j):
(i j) can utilize integrogram technology to be accelerated to calculate C.Wherein, W is default slip
The size of window.By formula it will be seen that (i, scope j) is due to field of direction O of fingerprint image
0~180 °, then (i, scope j) is exactly 0~360 ° to field of direction 2O of fingerprint image.If fingerprint image
The field of direction of picture varies less (O (i j) is constant) under extreme case, then the result of above formula is permanent
It is 1.If field of direction change is abundant, (under extreme case, (i j) is evenly distributed in w window O
0~180 °), cos item and sin item are equivalent to integration within a cycle, then the result of above formula is permanent
It is 0.That is fingerprint image concordance image C (i, j) between 0~1, C (i, j) the least
Orientation consistency is the strongest, and vice versa, such that it is able to estimate the definition of fingerprint image.
Seeing also Fig. 4 and Fig. 5, Fig. 4 is that definition preferably frame fingerprint image is converted to refer to
The schematic diagram of the print image field of direction.Fig. 5 is that the frame fingerprint image that definition is not enough is converted to fingerprint image
Schematic diagram as the field of direction.The field of direction of the fingerprint image shown in Fig. 4 be have along and direction change be gradually
Become, and the field of direction of the fingerprint image shown in figure is rambling.Therefore the direction of fingerprint image
The quality of field weighs the quality one important references factor of fingerprint image.
Step S23: according to concordance fingerprint image C (i, j) concordance score S of calculated direction fieldo:
So=| C (i, j) > To|/N
Wherein, | C (i, j) > To| represent that (i, j) more than the number of threshold value To, N is total pixel of image to C
Amount.In this step, the concordance score of the field of direction calculating fingerprint image accurately can be handed over, and
The calculating using less fingerprint recognition system processes resource.
The computational methods of the effective area of fingerprint image currently mainly utilize traditional background segment method,
The precision of this type of method is higher, but computing is complicated.Therefore the method that the present invention adds up based on gradient is entered
Row effective area is assessed, and has that amount of calculation is little and precision high advantage.
Refer to the effective area schematic diagram that Fig. 6, Fig. 6 are a second-rate frame fingerprint image.Figure
Fingerprint image shown in 6, due to user's pressing and the edge near fingerprint sensing matrix, collects fingerprint
Fingerprint lines in image the most all covers or covers a less frame fingerprint image picture so that this frame refers to
It is on the low side and cause fingerprint to refuse sincere rising that print image carries fingerprint characteristic dot information.Therefore fingerprint is being chosen
Image is necessary this kind of fingerprint image to get rid of by following fingerprint image calculation procedure.
Wherein, the effective area score calculating fingerprint image specifically comprises the following steps that
Step S24: calculate horizontal direction gradient and the vertical gradient of fingerprint image.In this step
In Zhou, respectively calculate fingerprint image f (i, horizontal direction gradient dx j) and vertical gradient dy:
dx(i, j)=f (and i+1, j)-f (i-1, j)
dy(i, j)=f (i, j+1)-f (i, j-1)
Step S25: calculate fingerprint image gradient amplitude image A (i, j):
Step S26: (i j) carries out statistics of sliding to gradient amplitude image A with the window of fixed size;
(i j) can utilize general integrogram technology to be accelerated solving to calculate H.
Step S27: calculate effective area score S of fingerprint image according to slip statistical resulta:
Sa=| H (i, j) > Ta|/N
Wherein, | H (i, j) > Ta| represent that (i, j) more than the number of threshold value Ta, N is total pixel of image to H.
When after effective area score Sa obtaining fingerprint image and orientation consistency score So, by right
Both are weighted summation can obtain comprehensive score S of final fingerprint image quality, and formula is as follows:
S=α1×Sa+α2×So
Wherein, α1+α2=1.
After calculating the comprehensive score of fingerprint image quality, proceed following steps:
Step S3, judge that quality comprehensive score S of fingerprint image is whether more than presetting score threshold s.
If step S4 judges whether quality comprehensive score S of fingerprint image is more than presets score threshold s,
Carry out mating and calculating matching score Q with the information in fingerprint prestored by current finger print image information;
Step S5, judge that matching score is whether more than preset matching score threshold q;If the step of being carried out
S6, otherwise prompting fingerprint does not mates;
Step S6, pass through fingerprint matching.
Refer to Fig. 7, the module map of fingerprint recognition system of the present invention.Described include at a fingerprint image
Reason module and a fingerprint sensing array,
Fingerprint sensing array, for obtaining a frame fingerprint image;
Described fingerprint image processing module includes:
Orientation field computation unit, calculates the concordance score of the field of direction of fingerprint image;
Effective area computing unit, calculates the effective area score of fingerprint image;
Score calculation unit, calculates fingerprint image according to concordance score and effective area score
Quality comprehensive score;
Judging unit, it is judged that whether quality comprehensive score is more than presetting score threshold, if being by referring to
Stricture of vagina data are mated, and otherwise, prompting user fingerprints does not mates.
In fingerprint identification process, fingerprint sensing array response user presses collection fingerprint image, fingerprint
Image processing module receives a frame fingerprint image.
Further, described fingerprint image processing module includes: matching score computing module, it is judged that refer to
Stricture of vagina matching score whether preset matching score threshold, if passing through fingerprint authentication.
Further, the concordance score of the field of direction of described orientation field computation unit calculating fingerprint image
Process is as follows:
First, calculate fingerprint image field of direction O (i, j).
Then, to field of direction O, (i, j) carrying out slides calculates the window of employing fixed size, it is thus achieved that one
Cause property fingerprint image C (i, j).
At present, assess fingerprint image definition aspect, the method presently mainly utilizing self study, be somebody's turn to do
Method is the most complicated, is unfavorable for reducing system cost.Therefore can estimate that image is clear based on following methods
Clear degree, reaches the feature that the little accuracy of amount of calculation is high.I.e. use the window of fixed size to O (i, j)
Carry out sliding and calculate, it is thus achieved that concordance image C (i, j):
(i j) can also utilize integrogram technology to be accelerated to calculate C.Wherein, W is default cunning
The size of dynamic window.By formula it will be seen that (i, scope j) is due to field of direction O of fingerprint image
0~180 °, then (i, scope j) is exactly 0~360 ° to field of direction 2O of fingerprint image.If fingerprint image
The field of direction of picture varies less (O (i j) is constant) under extreme case, then the result of above formula is permanent
It is 1.If field of direction change is abundant, (under extreme case, (i j) is evenly distributed in w window O
0~180 °), cos item and sin item are equivalent to integration within a cycle, then the result of above formula is permanent
It is 0.That is fingerprint image concordance image C (i, j) between 0~1, C (i, j) the least
Orientation consistency is the strongest, and vice versa, such that it is able to estimate the definition of fingerprint image.
Finally, according to concordance fingerprint image C (i, j) concordance score S of calculated direction fieldo:
So=| C (i, j) > To|/N
Wherein, | C (i, j) > To| represent that (i, j) more than the number of threshold value To, N is total pixel of image to C
Amount.In this step, the concordance score of the field of direction calculating fingerprint image accurately can be handed over, and
The calculating using less fingerprint recognition system processes resource.
Further, described effective area computing unit calculates the effective area score process of fingerprint image
As follows:
First, respectively calculate fingerprint image f (i, horizontal direction gradient dx j) and vertical gradient dy:
dx(i, j)=f (and i+1, j)-f (i-1, j)
dy(i, j)=f (i, j+1)-f (i, j-1)
Then, calculate fingerprint image gradient amplitude image A (i, j):
Again, with the window of fixed size, to gradient amplitude image A, (i j) carries out statistics of sliding;
Can utilize general integrogram technology be accelerated calculate H (i, j).
Finally, effective area score S of fingerprint image is calculated according to slip statistical resulta:
Sa=| H (i, j) > Ta|/N
Wherein, | H (i, j) > Ta| represent that (i, j) more than the number of threshold value Ta, N is total pixel of image to H.
The matter of fingerprint image is evaluated by fingerprint image effective area and two dimensions of orientation consistency
Amount.After calculating effective area score Sa and orientation consistency score So obtaining fingerprint image, logical
Crossing is weighted both suing for peace can obtain quality comprehensive score S of final fingerprint image.Referring to
During stricture of vagina identification, it is ensured that use quality comprehensive score S high value and the preset fingerprint number of fingerprint image
According to coupling, reduce refusing sincere and improve the reliable of fingerprint recognition of fingerprint recognition.
Despite with reference to each embodiment, the disclosure is described, it will be appreciated that these embodiments are to say
Bright property, and the scope of the present invention is not limited only to them.Many change, revise, add and
It is all possible for improving.More generally, it is at particular implementation according to each embodiment disclosed by the invention
Described in the context of example.Function can be during the course with not in each embodiment disclosed by the invention
Same mode separately or in combination, or utilizes different terms to describe.These and other change, amendment,
Adding and improve can be in scope disclosed by the invention as defined in subsequent claim
In.
Claims (10)
1. a fingerprint identification method, it is characterised in that said method comprising the steps of:
Step S1, obtain a fingerprint image;
Step S2, calculate the quality comprehensive score of fingerprint image;
Step S3, judge that the quality comprehensive score of fingerprint image is whether more than presetting score threshold;
If step S4 judges that the quality comprehensive score of fingerprint image, ought more than presetting score threshold
Front information in fingerprint carries out mating and calculating matching score with the information in fingerprint prestored;
Step S5, judge that matching score is whether more than preset matching score threshold;If the step of being carried out
S6, otherwise prompting fingerprint does not mates;
Step S6, pass through fingerprint matching.
Fingerprint identification method the most according to claim 1, it is characterised in that described fingerprint recognition
Method is further comprising the steps of:
Step S7: the quality comprehensive score of fingerprint image is less than or equal to preset score threshold if judging,
Calculate the statistics number of fingerprint image quality score;
Step S8: judge that whether the quality score statistics number of fingerprint image is less than presetting statistics number
Threshold value, if being carried out step S1, otherwise prompting fingerprint does not mates.
Fingerprint identification method the most according to claim 1 and 2, it is characterised in that step S2:
Calculate the quality comprehensive score of fingerprint image, including:
Calculate the concordance score of the field of direction of fingerprint image;
Calculate the effective area score of fingerprint image;With
By the concordance score of the field of direction of calculated fingerprint image and calculated fingerprint image
The effective area score of picture is weighted summation to obtain the comprehensive score of fingerprint image quality.
Fingerprint identification method the most according to claim 3, it is characterised in that calculate fingerprint image
The concordance score of the field of direction, comprise the following steps:
Step S21: calculate fingerprint image field of direction O (i, j);
Step S22: use fixed size window to field of direction O (i, j) carrying out slide calculate, it is thus achieved that
Concordance fingerprint image C (i, j);
Step S23: according to concordance fingerprint image C (i, j) the concordance score of calculated direction field.
Fingerprint identification method the most according to claim 3, it is characterised in that calculate fingerprint image
Effective area score, comprise the following steps:
Step S24: calculate horizontal direction gradient and the vertical gradient of fingerprint image;
Step S25: calculate fingerprint image gradient amplitude image A (i, j);
Step S26: (i j) carries out statistics of sliding to gradient amplitude image A with the window of fixed size;
Step S27: calculate the effective area score of fingerprint image according to slip statistical result.
6. a fingerprint recognition system, it is characterised in that described fingerprint recognition system includes a fingerprint image
As processing module and a fingerprint sensing array,
Fingerprint sensing array, for obtaining a frame fingerprint image;
Described fingerprint image processing module includes:
Orientation field computation unit, calculates the concordance score of the field of direction of fingerprint image;
Effective area computing unit, calculates the effective area score of fingerprint image;
Score calculation unit, calculates fingerprint image according to concordance score and effective area score
Quality comprehensive score;
Judging unit, it is judged that whether quality comprehensive score is more than presetting score threshold, if being by
Finger print data mates, and otherwise, prompting user fingerprints does not mates.
Fingerprint recognition system the most according to claim 6, it is characterised in that described fingerprint image
Processing module includes:
Matching score computing module, it is judged that fingerprint matching score whether preset matching score threshold, if
Then pass through fingerprint authentication.
Fingerprint recognition system the most according to claim 6, it is characterised in that described field of direction meter
Calculation unit passes through:
Calculate fingerprint image field of direction O (i, j);
To field of direction O, (i, j) carrying out slides calculates the window of employing fixed size, it is thus achieved that concordance refers to
Print image C (i, j);According to concordance fingerprint image C (i, j) the concordance score of calculated direction field.
Fingerprint recognition system the most according to claim 6, it is characterised in that described effective area
Computing unit passes through:
Calculate horizontal direction gradient and the vertical gradient of fingerprint image;
Calculate fingerprint image gradient amplitude image A (i, j);
With the window of fixed size, to gradient amplitude image A, (i j) carries out statistics of sliding;
The effective area score of fingerprint image is calculated according to slip statistical result.
10. an electronic equipment, it is characterised in that described electronic equipment includes appointing in claim 6-9
Anticipate a described fingerprint recognition system.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610379150.7A CN106096513A (en) | 2016-06-01 | 2016-06-01 | Fingerprint identification method, fingerprint recognition system and electronic equipment |
PCT/CN2017/086650 WO2017206914A1 (en) | 2016-06-01 | 2017-05-31 | Fingerprint recognition method, fingerprint recognition system, and electronic device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610379150.7A CN106096513A (en) | 2016-06-01 | 2016-06-01 | Fingerprint identification method, fingerprint recognition system and electronic equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106096513A true CN106096513A (en) | 2016-11-09 |
Family
ID=57230552
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610379150.7A Pending CN106096513A (en) | 2016-06-01 | 2016-06-01 | Fingerprint identification method, fingerprint recognition system and electronic equipment |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN106096513A (en) |
WO (1) | WO2017206914A1 (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107111762A (en) * | 2017-03-20 | 2017-08-29 | 深圳市汇顶科技股份有限公司 | Fingerprint identification method and device |
CN107169466A (en) * | 2017-05-25 | 2017-09-15 | 北京东方金指科技有限公司 | A kind of palmprint image quality overall evaluation method based on sum of ranks ratio method |
WO2017206914A1 (en) * | 2016-06-01 | 2017-12-07 | 深圳信炜科技有限公司 | Fingerprint recognition method, fingerprint recognition system, and electronic device |
CN107690655A (en) * | 2017-09-04 | 2018-02-13 | 深圳市汇顶科技股份有限公司 | Fingerprint register method, apparatus and electric terminal |
CN109409962A (en) * | 2018-11-08 | 2019-03-01 | 北京旷视科技有限公司 | Image processing method, device, electronic equipment, computer readable storage medium |
CN109815935A (en) * | 2019-02-20 | 2019-05-28 | Oppo广东移动通信有限公司 | Electronic device, fingerprint authentication method and Related product |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI693554B (en) * | 2019-02-21 | 2020-05-11 | 大陸商北京集創北方科技股份有限公司 | Processing method for improving security of fingerprint recognition device, fingerprint recognition device and information processing device |
CN114359982B (en) * | 2022-03-19 | 2022-05-27 | 广州格鲁信息技术有限公司 | Anti-fraud system and method based on big data processing |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1480896A (en) * | 2002-09-04 | 2004-03-10 | �����������������ͳ��ʶ������ | Fingerprint identification method as well as fingerprint controlling method and system |
CN101030246A (en) * | 2007-04-09 | 2007-09-05 | 黄东运 | Method for discriminating fingerprint |
US8605959B2 (en) * | 2008-12-22 | 2013-12-10 | International Business Machines Corporation | Apparatus, system, and method for sequenced biometric authentication |
CN104809453A (en) * | 2015-05-19 | 2015-07-29 | 成都英力拓信息技术有限公司 | Authentication method based on fingerprints |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103824060A (en) * | 2014-02-28 | 2014-05-28 | 清华大学 | Method for extracting fingerprint detail points |
CN104463132B (en) * | 2014-12-17 | 2018-09-11 | 浙江维尔科技股份有限公司 | A kind of fingerprint identification method and device |
CN106096513A (en) * | 2016-06-01 | 2016-11-09 | 深圳信炜科技有限公司 | Fingerprint identification method, fingerprint recognition system and electronic equipment |
-
2016
- 2016-06-01 CN CN201610379150.7A patent/CN106096513A/en active Pending
-
2017
- 2017-05-31 WO PCT/CN2017/086650 patent/WO2017206914A1/en active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1480896A (en) * | 2002-09-04 | 2004-03-10 | �����������������ͳ��ʶ������ | Fingerprint identification method as well as fingerprint controlling method and system |
CN101030246A (en) * | 2007-04-09 | 2007-09-05 | 黄东运 | Method for discriminating fingerprint |
US8605959B2 (en) * | 2008-12-22 | 2013-12-10 | International Business Machines Corporation | Apparatus, system, and method for sequenced biometric authentication |
CN104809453A (en) * | 2015-05-19 | 2015-07-29 | 成都英力拓信息技术有限公司 | Authentication method based on fingerprints |
Non-Patent Citations (2)
Title |
---|
张祖泷: "基于多因子的指纹图像质量评价方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
杨鑫等: "《生物特征识别理论与应用》", 31 December 2009 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017206914A1 (en) * | 2016-06-01 | 2017-12-07 | 深圳信炜科技有限公司 | Fingerprint recognition method, fingerprint recognition system, and electronic device |
CN107111762A (en) * | 2017-03-20 | 2017-08-29 | 深圳市汇顶科技股份有限公司 | Fingerprint identification method and device |
CN107169466A (en) * | 2017-05-25 | 2017-09-15 | 北京东方金指科技有限公司 | A kind of palmprint image quality overall evaluation method based on sum of ranks ratio method |
CN107169466B (en) * | 2017-05-25 | 2020-03-31 | 北京东方金指科技有限公司 | Palm print image quality comprehensive evaluation method based on rank-sum ratio method |
CN107690655A (en) * | 2017-09-04 | 2018-02-13 | 深圳市汇顶科技股份有限公司 | Fingerprint register method, apparatus and electric terminal |
WO2019041342A1 (en) * | 2017-09-04 | 2019-03-07 | 深圳市汇顶科技股份有限公司 | Fingerprint registration method and device and electronic terminal |
CN109409962A (en) * | 2018-11-08 | 2019-03-01 | 北京旷视科技有限公司 | Image processing method, device, electronic equipment, computer readable storage medium |
CN109815935A (en) * | 2019-02-20 | 2019-05-28 | Oppo广东移动通信有限公司 | Electronic device, fingerprint authentication method and Related product |
Also Published As
Publication number | Publication date |
---|---|
WO2017206914A1 (en) | 2017-12-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106096513A (en) | Fingerprint identification method, fingerprint recognition system and electronic equipment | |
CN105631439B (en) | Face image processing process and device | |
Wasnik et al. | Assessing face image quality for smartphone based face recognition system | |
CN105956582A (en) | Face identifications system based on three-dimensional data | |
US20190139262A1 (en) | Method and device for vehicle identification | |
CN104239856B (en) | Face identification method based on Gabor characteristic and self adaptable linear regression | |
CN105809125A (en) | Multi-core ARM platform based human face recognition system | |
CN107832802A (en) | Quality of human face image evaluation method and device based on face alignment | |
CN104809452A (en) | Fingerprint identification method | |
CN103262118A (en) | Attribute value estimation device, attribute value estimation method, program, and recording medium | |
CN102567744B (en) | Method for determining quality of iris image based on machine learning | |
CN105844206A (en) | Identity authentication method and identity authentication device | |
KR20170006355A (en) | Method of motion vector and feature vector based fake face detection and apparatus for the same | |
CN108596087A (en) | A kind of driving fatigue degree detecting regression model based on dual network result | |
CN106940791B (en) | A kind of pedestrian detection method based on low-dimensional histograms of oriented gradients | |
CN104809453A (en) | Authentication method based on fingerprints | |
CN101587541A (en) | Character recognition method based on human body contour outline | |
CN110674680B (en) | Living body identification method, living body identification device and storage medium | |
CN109376609A (en) | Recognition methods, device and the intelligent terminal of pantograph abrasion | |
CN101582113A (en) | Method for identifying face image with identity through layered comparison | |
CN104091173A (en) | Gender recognition method and device based on network camera | |
CN108009574A (en) | A kind of rail clip detection method | |
Yao et al. | An improved feature-based method for fall detection | |
US11494918B2 (en) | Moving state analysis device, moving state analysis method, and program | |
CN106446837B (en) | A kind of detection method of waving based on motion history image |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161109 |
|
RJ01 | Rejection of invention patent application after publication |